Downloads · 30 days
2
10% of all-time downloads
eval_transliterated
Priyanship/eval_transliterated
eval_transliterated is a automatic speech recognition model from Priyanship. Use it when you need speech turned into text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
20
Public
Parameters
316M
1.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.3 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- Model type
- wav2vec2
- Access
- Public
- Created
- Oct 14, 2024
- Updated
- Oct 14, 2024
- SHA
- bb6ad58e
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
eval_transliterated
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- eval_loss: 2.2188
- eval_model_preparation_time: 0.0054
- eval_cer: 0.3354
- eval_wer: 0.4724
- eval_runtime: 31.1696
- eval_samples_per_second: 18.351
- eval_steps_per_second: 1.155
- step: 0
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0006
- train_batch_size: 16
- eval_batch_size: 16
- seed: 300
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 1000
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.45.2
- Pytorch 2.4.0
- Datasets 2.20.0
- Tokenizers 0.20.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- Created
- Oct 14, 2024
- Updated
- Oct 14, 2024